© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 125173
    Prev
    Next
    INDEX
    Explanations

    network

    np_max-act · gemini-2.0-flash

    The neuron fires on numeric values (digits and decimal numbers) in the API documentation.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    손
    -0.07
    بال
    -0.07
    ẳ
    -0.07
     Mayer
    -0.07
    suit
    -0.06
     ACM
    -0.06
    iotics
    -0.06
    اخر
    -0.06
    akh
    -0.06
    *(
    -0.06
    POSITIVE LOGITS
    property
    0.06
    	          
    0.06
    Apis
    0.06
     пользоват
    0.06
     agile
    0.06
     неж
    0.06
     uncon
    0.06
    ="#">
    0.06
     SOUND
    0.06
     phương
    0.06
    Activations Density 0.002%

    No Known Activations